Date: Thu, 23 Feb 2017 11:40:21 +0800 From: Sepherosa Ziehau <sepherosa@gmail.com> To: Gleb Smirnoff <glebius@freebsd.org> Cc: Julien Charbon <jch@freebsd.org>, Jason Eggleston <jeggleston@llnw.com>, "freebsd-net@freebsd.org" <net@freebsd.org>, hiren@freebsd.org, jtl@freebsd.org, rrs@freebsd.org Subject: Re: listening sockets as non sockets Message-ID: <CAMOc5cw7fkrS6LVCwo1hXY459O9p5VdgyfcE4Apkc-kAgQWu7A@mail.gmail.com> In-Reply-To: <20170222232704.GJ8899@FreeBSD.org> References: <20170127005251.GM2611@FreeBSD.org> <20170210063024.GE1973@FreeBSD.org> <20170216184903.GF58829@FreeBSD.org> <0858647a-ec3c-1a78-053f-d04397a82d8a@freebsd.org> <20170222232704.GJ8899@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Feb 23, 2017 at 7:27 AM, Gleb Smirnoff <glebius@freebsd.org> wrote: > On Tue, Feb 21, 2017 at 09:58:45AM +0100, Julien Charbon wrote: > J> > T> 1) The patch worked pretty okay, but the idea of separate file type is > J> > T> abandoned. With current filedescriptor code it is almost impossible > J> > T> to racelessly switch fileops and f_data. > J> > T> For more details read the commit message, URL below. > J> > T> > J> > T> 2) I moved the work to git. It allows for easier code sharing. > J> > T> > J> > T> https://github.com/glebius/FreeBSD/commit/3a52df429889ea9c6e61013f6913aad95939f159 > J> > > J> > The current 'solisten' branch at https://github.com/glebius/FreeBSD has > J> > been running successfully for 48 hours at Netflix. But as mentioned before, > J> > our connection rate is pretty low. > J> > > J> > So, testing from Julien and Hiren will be much appreciated. > J> > J> Sound good, I will have spare time to get performance results on our > J> side w/ and w/o your change before the end of this week. > > Thanks, Julien! Looking forward for your results. Meanwhile, the code has > been running for a week on a single Netflix box. And for 24 hours on a > set of boxes as A/B test against non-patched code. Since our connection > rate is low, and we never seen accept_mtx to be a major problem in our > profiling, the A/B test didn't show any statistically significant > improvements. But my biased eye of course sees some improvements in the > graphs :) You can use this to force clients to generate 1 request/connection (--connreqs 1) to test the accept queue contention for HTTP workload: https://github.com/sepherosa/wrk Checkout the sephe/wrk branch. pkg install wrk. Then gmake in the checked out directory. Thanks, sephe -- Tomorrow Will Never Die
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAMOc5cw7fkrS6LVCwo1hXY459O9p5VdgyfcE4Apkc-kAgQWu7A>